INDEX

Explanations

before/since

np_max-act-logits · gemini-2.0-flash

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

IFrame

Link

Negative Logits

val

-0.25

 lifetime

-0.25

Cour

-0.24

é¢ľ

-0.24

Trace

-0.24

unc

-0.24

éĹ¨

-0.24

 ÑĤÐ¾Ð²Ð°ÑĢ

-0.24

opath

-0.23

isci

-0.23

POSITIVE LOGITS

 independence

0.29

 robot

0.29

Ĥ¨

0.28

 connections

0.27

éĢģåİ»

0.27

 Expansion

0.27

çļĦæĹ¶éĹ´

0.27

robot

0.27

Independ

0.27

casting

0.26

Activations Density 0.002%

before/since

No Known Activations