INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

inst

-0.28

 tiá»ģn

-0.26

 exceeding

-0.26

å·²ç»ıè¶ħè¿ĩ

-0.26

preced

-0.25

æĴ¬

-0.25

Coder

-0.25

æĢĿãĤı

-0.25

åŀ«

-0.24

mention

-0.24

POSITIVE LOGITS

cru

0.28

etre

0.28

è¿ĻæĿ¡

0.27

åīľ

0.25

 Holt

0.25

 Sail

0.25

igth

0.25

éªĬ

0.24

_REPLACE

0.24

lug

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.