INDEX

Explanations

Space and research

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

å±Ģ

-0.28

equ

-0.27

èĮĥåĽ´

-0.26

é£İæł¼

-0.26

 femin

-0.26

inge

-0.25

ç¼ºå¤±

-0.25

èĺ§

-0.25

-wrap

-0.25

 styles

-0.25

POSITIVE LOGITS

maj

0.29

apist

0.28

 Cree

0.27

_partitions

0.27

agal

0.25

æ³¡æ³¡

0.25

,address

0.25

deps

0.25

mez

0.25

CNT

0.24

Activations Density 0.011%

Space and research

No Comments

No Known Activations