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

 plaster

-0.29

moth

-0.27

orsch

-0.27

lund

-0.26

leta

-0.25

IDA

-0.24

 PARTICULAR

-0.24

estroy

-0.24

oya

-0.24

éŀ£

-0.24

POSITIVE LOGITS

 Concent

0.25

 concentration

0.24

èĥ½åĲ¦

0.24

æľīåĲį

0.24

AMESPACE

0.24

scroll

0.23

AGING

0.23

 arrangements

0.23

è¢«æ·ĺæ±°

0.23

 concentrations

0.23

Activations Density 0.013%

No Known Activations

This feature has no known activations.