INDEX

Explanations

negative events

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

·¨

-0.33

äº¤

-0.27

_COMPILE

-0.26

çĽ´

-0.26

 propagated

-0.25

unning

-0.25

ician

-0.24

à¹īà¸²à¸¢

-0.24

æľºæ¢°

-0.24

 mixed

-0.24

POSITIVE LOGITS

ologne

0.27

tsy

0.27

etsk

0.26

åĪłéĻ¤æĪĲåĬŁ

0.26

ICS

0.26

 Kirst

0.25

 infl

0.25

ishly

0.24

åĳ

0.24

è´§

0.24

Activations Density 0.009%

negative events

No Comments

No Known Activations