INDEX

Explanations

simple explanations/instructions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

annes

-0.27

.mods

-0.26

æ³Ħ

-0.26

 offence

-0.26

ç½©

-0.26

anus

-0.26

 ransom

-0.25

SError

-0.25

soever

-0.25

 objection

-0.25

POSITIVE LOGITS

osate

0.27

æĲŃ

0.27

icker

0.26

mez

0.26

 closest

0.25

ä»Ģä¹Īåĳ¢

0.25

 comple

0.24

éĹ¾

0.24

æ¯ıå¤©éĥ½

0.24

 baker

0.24

Activations Density 0.038%

simple explanations/instructions

No Comments

No Known Activations