INDEX

Explanations

Code/URLs snippets

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

orts

-0.32

apy

-0.31

ableObject

-0.29

 mocks

-0.27

å¿«éĢŁå¢ŀéķ¿

-0.26

 Encounter

-0.26

avers

-0.25

tright

-0.25

çį¨

-0.24

 CASE

-0.24

POSITIVE LOGITS

å¸¦æĿ¥çļĦ

0.27

è°¨

0.26

 depletion

0.25

 ModelState

0.25

åħħ

0.25

-scalable

0.24

ÑĥÐ¼Ð°

0.24

<usize

0.24

hub

0.23

èĢĹ

0.23

Activations Density 1.018%

Code/URLs snippets

No Comments

No Known Activations