INDEX

Explanations

Code/titles/references

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

udas

-0.29

-dismiss

-0.27

elim

-0.27

 Elim

-0.27

ummer

-0.26

 elim

-0.26

 pitches

-0.26

 compens

-0.25

pitch

-0.25

zel

-0.24

POSITIVE LOGITS

 Memory

0.28

è®°å¿Ĩ

0.27

 è¾

0.26

ä¸įè´Ł

0.25

ç»ıåħ¸çļĦ

0.25

å¥¥åľ°

0.25

 Twice

0.25

 memory

0.25

Paren

0.24

æİ¥

0.24

Activations Density 0.006%

Code/titles/references

No Comments

No Known Activations