INDEX

Explanations

technical/mixed content

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

uze

-0.27

getNode

-0.26

 Asked

-0.26

ä¸Ģå®¶

-0.26

aal

-0.25

_FINAL

-0.25

Asked

-0.25

erta

-0.25

 onRequest

-0.25

thal

-0.24

POSITIVE LOGITS

ç®´

0.28

_prep

0.28

åĽ¾çº¸

0.27

spec

0.27

Spec

0.26

 sworn

0.26

hints

0.25

 symbolism

0.25

ynthesis

0.24

angep

0.24

Activations Density 0.001%

technical/mixed content

No Comments

No Known Activations