INDEX

Explanations

environment

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

atab

-0.28

ert

-0.27

↵      ↵

-0.25

BCE

-0.25

çĽĺçĤ¹

-0.25

unce

-0.24

lename

-0.24

ERT

-0.24

 seas

-0.24

 purported

-0.24

POSITIVE LOGITS

å¤ªé«ĺ

0.28

è·Ŀç¦»

0.27

 complement

0.26

bish

0.26

å®¶éĹ¨åı£

0.26

ç¬ł

0.25

ivos

0.25

éĻį

0.25

æ¸¥

0.24

 Riding

0.24

Activations Density 0.004%

environment

No Comments

No Known Activations