INDEX

Explanations

histone deacetylation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

èĪĽ

-0.29

cplusplus

-0.28

 Goldman

-0.27

rets

-0.25

exh

-0.25

èĥ½æ»¡è¶³

-0.24

ansa

-0.23

ah

-0.23

ksi

-0.23

è¿ĩç¨ĭ

-0.23

POSITIVE LOGITS

icut

0.28

åł¡

0.26

éĻµ

0.25

 directions

0.24

inc

0.23

 feast

0.23

åŃ¤

0.23

]|

0.23

 traffic

0.23

traffic

0.23

Activations Density 0.002%

histone deacetylation

No Comments

No Known Activations