INDEX

Explanations

coding and technical jargon

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

 levels

-0.29

Plans

-0.28

loud

-0.28

ouden

-0.27

 æĸ

-0.27

-links

-0.27

 Levels

-0.27

plans

-0.26

çĵ¢

-0.26

.levels

-0.26

POSITIVE LOGITS

abilia

0.27

æŁ¥è¯¢

0.27

(Dense

0.26

¶ļ

0.26

hit

0.25

hit

0.25

 fetching

0.25

ç£

0.24

 seeded

0.24

 query

0.24

Activations Density 0.017%

coding and technical jargon

No Comments

No Known Activations