INDEX

Explanations

sight

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

olan

-0.28

 buck

-0.28

ogens

-0.26

æľĢåĲĪéĢĤ

-0.25

 doubt

-0.25

abel

-0.25

lev

-0.24

Interest

-0.24

ç¯ĵ

-0.24

omed

-0.24

POSITIVE LOGITS

èµĵ

0.28

æ³³

0.25

å±į

0.25

privacy

0.24

(po

0.24

åºŃ

0.24

 distances

0.24

AndView

0.24

æĥ¨

0.24

Æ¡i

0.24

Activations Density 0.003%

sight

No Comments

No Known Activations