INDEX

Explanations

Medical suffixes/prefixes

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

 note

-0.30

 decom

-0.28

ä¸ºåŁºç¡Ģ

-0.27

Gra

-0.26

IM

-0.26

 táºŃn

-0.26

ta

-0.26

åŁºç¡Ģä¸Ĭ

-0.25

[x

-0.25

pro

-0.25

POSITIVE LOGITS

icum

0.36

)>>

0.31

.DataAccess

0.29

gesch

0.29

.tie

0.27

pread

0.26

getList

0.26

<<<

0.26

ibri

0.25

 Gesch

0.25

Activations Density 0.008%

Medical suffixes/prefixes

No Comments

No Known Activations