INDEX

Explanations

alphanumeric identifiers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

spent

-0.29

gul

-0.28

nist

-0.28

å¸¸åĬ¡

-0.26

morgan

-0.26

 spent

-0.26

dent

-0.25

è°į

-0.25

æ°ĳæĦı

-0.25

æ²³æ°´

-0.25

POSITIVE LOGITS

æĭĽ

0.30

Leg

0.27

áº·p

0.26

otto

0.26

atories

0.25

ature

0.25

leg

0.25

Ð±Ð°ÑĢ

0.24

 Reserve

0.24

-pointer

0.24

Activations Density 0.002%

alphanumeric identifiers

No Comments

No Known Activations