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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĬ¥å¤į

-0.27

 Impress

-0.26

 poisoned

-0.25

ialis

-0.25

,dim

-0.24

åĩĨç¡®

-0.24

erring

-0.24

ager

-0.24

æ¸¸

-0.24

ÐºÑĢÐµÐ¿

-0.23

POSITIVE LOGITS

 DataFrame

0.27

(Profile

0.26

ificio

0.26

igth

0.25

 AuthService

0.25

odb

0.24

AuthService

0.24

(Handle

0.24

çīĤ

0.24

æº

0.23

Activations Density 0.020%

No Known Activations

This feature has no known activations.