INDEX

Explanations

Providing or being in a state

np_max-act · gemini-2.0-flash

past participle verbs ending in “-ed,” especially when used in passive constructions or as adjectival modifiers.

oai_token-act-pair · gpt-5 Triggered by @liuliujiujiu05

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¾Ĺè½¬

-0.28

ä¸Ĭåİ»

-0.27

ä¸Ģå¤ľ

-0.25

 inherit

-0.25

avax

-0.24

criptors

-0.24

åħ½

-0.24

 ÐľÐ¾

-0.24

uem

-0.24

âį¨

-0.23

POSITIVE LOGITS

ä¸įæŃ»

0.27

agger

0.27

ä¸İåĲ¦

0.27

å¦Ĥæŀľæľī

0.25

hic

0.25

ancing

0.25

ton

0.24

appa

0.24

Post

0.23

åħ¬å®īå±Ģ

0.23

Activations Density 5.782%

Providing or being in a state

past participle verbs ending in “-ed,” especially when used in passive constructions or as adjectival modifiers.

No Comments

No Known Activations