INDEX

Explanations

Names and technical terms

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

taskId

-0.26

æīİ

-0.26

knowledge

-0.25

çĹĽ

-0.25

ling

-0.25

ç©¿

-0.25

 dress

-0.24

aining

-0.24

èĦ±

-0.24

PRESS

-0.24

POSITIVE LOGITS

ä¸ªåĪ«

0.30

mo

0.29

èŃ¬

0.28

ogui

0.27

mo

0.27

Mo

0.26

rief

0.26

çªł

0.26

è½¬æĬĺ

0.26

ried

0.26

Activations Density 0.898%

Names and technical terms

No Comments

No Known Activations