INDEX

Explanations

to be

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

å±Ĭ

-0.29

åĬŀå¥½

-0.27

ocation

-0.27

åıĪå¥½åıĪå¿«

-0.26

 epoch

-0.25

 Kath

-0.25

Thr

-0.25

ograd

-0.25

æĢİä¹ĪåĬŀ

-0.25

è¸µ

-0.25

POSITIVE LOGITS

FFE

0.27

TEM

0.26

metic

0.26

pov

0.26

 pressures

0.25

ITT

0.25

ipur

0.25

è¡¨è¾¾

0.25

åİĭ

0.25

åİĭåĬĽ

0.25

Activations Density 0.057%

to be

No Comments

No Known Activations