INDEX

Explanations

that

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

å¨ģèĥģ

-0.28

æĭĩæĮĩ

-0.27

manuel

-0.26

 swear

-0.25

çľĭä»ĸ

-0.25

åĲĦåĮº

-0.24

UGC

-0.24

unya

-0.24

apos

-0.24

[at

-0.23

POSITIVE LOGITS

èĲ½åĲİ

0.28

robe

0.26

AccessException

0.26

anders

0.26

 PROF

0.26

ingle

0.25

èŃ·

0.25

 rÃ³Å¼

0.25

prof

0.25

icious

0.25

Activations Density 0.002%

that

No Comments

No Known Activations