INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

åĨįä¹Ł

-0.27

éģĴ

-0.26

 BaseModel

-0.26

rium

-0.26

 ApiController

-0.24

äºĨä¸įå°ĳ

-0.24

Gry

-0.24

::$

-0.24

HostException

-0.23

iento

-0.23

POSITIVE LOGITS

æĸ½

0.30

éĹªçĶµ

0.27

 instruct

0.26

elle

0.25

Ã¼z

0.25

ocks

0.25

PBS

0.24

 bers

0.24

 Bers

0.24

 pulses

0.24

Activations Density 0.019%

No Known Activations

This feature has no known activations.