INDEX

Explanations

isser

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 inconsistencies

-0.27

agit

-0.27

æ¬¡ä¼ļè®®

-0.26

ä¸įæľį

-0.26

Sok

-0.26

stry

-0.26

agedList

-0.25

çĲı

-0.24

pedo

-0.24

ouston

-0.24

POSITIVE LOGITS

Dur

0.29

uml

0.28

åĳĽ

0.28

dur

0.26

Dur

0.26

rian

0.25

_Str

0.25

çī¹æķĪ

0.25

èĮ±

0.25

 Marr

0.25

Activations Density 0.000%

isser

No Comments

No Known Activations