INDEX

Explanations

No Explanations Found

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

sist

-0.28

//<

-0.27

è¾ħåĬ©

-0.26

åı¸

-0.26

è¿ĩåİ»

-0.25

ajan

-0.25

Aux

-0.25

æŃ¤

-0.25

egrator

-0.24

å¸¸

-0.24

POSITIVE LOGITS

“

0.27

 qualifying

0.27

ByExample

0.25

“He

0.25

Vict

0.25

“She

0.25

 Routine

0.25

abr

0.25

æīĵæī°

0.24

 routine

0.24

Activations Density 0.009%

No Known Activations

This feature has no known activations.